E-NoseFlavNet: Towards E-Nose based Aroma Flavour Analysis Empowered by Diverse ML Models via Sensor Array Technology
Mühendislik Bilimleri ve Araştırmaları Dergisi · 30.04.2026 · 8 (1) · 67-76
DOI: 10.46387/bjesr.1854260 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mühendislik Bilimleri ve Araştırmaları Dergisi, online erschienen am 30.04.2026. Verfasst von İlyas Özer und 3 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben.
Abstract (Originalsprache)
Ensuring food-supply safety requires reliable aroma/flavour detection, yet conventional tools (test paper, cyclotron, chromatography) often lack accuracy, broad detection range, speed, portability, and low cost. We propose a sensor array electronic nose (E nose) for aroma VOC analysis and prediction, combining statistical visualization/discrimination (t SNE, MANOVA) with machine learning models. Five classes were studied: chocolate, clove, cinnamon, ginger, and an unflavoured VOC set. Using a literature benchmark of 95.73% accuracy, we evaluated Random Forest, ExtraTrees, XGBoost, CatBoost, and a Stacking ensemble for 5 class prediction and one vs rest tests. All models perfectly identified chocolate in one vs rest prediction. Stacking performed poorly for unflavoured vs others (50%), whereas other aromas reached up to 94%. Statistical methods showed clear VOC separation, especially in one vs rest analyses.
Zitieren
APA
Özer, İ., Çetin, O., Görür, K., & Temurtaş, F. (2026). E-NoseFlavNet: Towards E-Nose based Aroma Flavour Analysis Empowered by Diverse ML Models via Sensor Array Technology. Mühendislik Bilimleri ve Araştırmaları Dergisi, 8(1), 67-76. https://doi.org/10.46387/bjesr.1854260
Vancouver
Özer İ, Çetin O, Görür K, Temurtaş F. E-NoseFlavNet: Towards E-Nose based Aroma Flavour Analysis Empowered by Diverse ML Models via Sensor Array Technology. Mühendislik Bilimleri ve Araştırmaları Dergisi. 2026;8(1):67-76. doi:10.46387/bjesr.1854260
BibTeX
@article{zer2026,
author = {Özer, İlyas and Çetin, Onursal and Görür, Kutlucan and Temurtaş, Feyzullah},
title = {E-NoseFlavNet: Towards E-Nose based Aroma Flavour Analysis Empowered by Diverse ML Models via Sensor Array Technology},
journal = {Mühendislik Bilimleri ve Araştırmaları Dergisi},
year = {2026},
volume = {8},
number = {1},
pages = {67--76},
doi = {10.46387/bjesr.1854260}
}
EUVIMED